Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 175
    Prev
    Next
    INDEX
    Explanations

    words related to a strong, stable base or origin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of foundational concepts or elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ameless
    -0.73
    quit
    -0.68
    usterity
    -0.67
    azes
    -0.66
    essions
    -0.64
    cffff
    -0.64
    uel
    -0.62
    opers
    -0.62
    sweet
    -0.61
    Pacific
    -0.60
    POSITIVE LOGITS
     foundation
    1.12
     stone
    1.04
     groundwork
    1.02
     foundations
    0.95
     underpin
    0.93
     stones
    0.91
     laid
    0.90
     bedrock
    0.90
     framework
    0.89
     layer
    0.89
    Activations Density 0.079%

    No Known Activations